cxas-sim-eval

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from evaluation JSON files and conversation traces, which are interpolated into prompts for the Gemini model during the conversion and diagnostic stages.
  • Ingestion points: Evaluation data is read from JSON files in scripts/convert_eval.py and conversation logs are parsed in scripts/run_evals.py.
  • Boundary markers: The prompt templates for both conversion and analysis do not utilize explicit delimiters or instructions to prevent the model from following commands embedded within the input data.
  • Capability inventory: The skill scripts have permissions to perform file system operations, call Vertex AI Gemini APIs, and upload content to Google Cloud Storage.
  • Sanitization: No evidence of sanitization, validation, or escaping of the ingested data was found before it is passed to the language model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:19 PM
Security Audit — agent-trust-hub — cxas-sim-eval